Driving a car using reflexive fuzzy behaviors

VLSI fuzzy inferencing chips and a fuzzy behaviorist approach have been used to demonstrate the feasibility of driving a car under sensor-based autonomous navigation or driver´s aid mode using only sparse data from very inaccurate sensors. In the first mode, the car navigates fully autonomously, while in the second mode, the system acts as a driver´s aid providing the driver with linguistic commands to turn left or right and speed up or slow down depending on the obstacles perceived by the sensors. Experiments with both modes of control are described in which the system uses only three acoustic range sensor channels to perceive the environment. Simulation results as well as indoor and outdoor experiments are presented and discussed to illustrate the feasibility of autonomous navigation and/or safety enhancing driver´s aid using the new fuzzy inferencing hardware system and humanlike reasoning schemes built with fuzzy behaviors